Improved particle-flow event reconstruction for future colliders using scalable neural networks.
problem Efficient and accurate particle reconstruction in future particle detectors.
method Comparative study of scalable machine learning models (graph neural network and kernel-based transformer) for event reconstruction.
result Graph neural network model improves jet transverse momentum resolution by up to 50%.
KM-GPT automates IPD reconstruction from KM plots with high accuracy and scalability.
problem Manual digitization of IPD from KM plots is error-prone and lacks scalability.
method KM-GPT integrates advanced image preprocessing, multi-modal reasoning, and iterative reconstruction algorithms.
result KM-GPT generates high-quality IPD without manual input or intervention, achieving superior accuracy.
dAUTOMAP scales AUTOMAP by decomposing domain transformation.
problem Inadequate scalability limits AUTOMAP's practicality.
method Decomposes AUTOMAP's domain transformation for linear scalability.
result dAUTOMAP outperforms AUTOMAP with fewer parameters.
Theory reconstructs network connectivity from event timings.
problem Reconstructing network connectivity from incomplete continuous-time data.
method Linearizes event space mapping to reveal direct influences.
result Reveals synapse presence and inhibitory/activating nature.
MLPF uses graph neural networks to improve particle-flow reconstruction in high-pileup conditions.
problem Improving particle-flow reconstruction in high-pileup conditions at high-luminosity LHC.
method End-to-end trainable machine-learned particle-flow algorithm based on graph neural networks.
result MLPF improves physics response and demonstrates scalable reconstruction in high-pileup environments.
Method reconstructs networks and identifies communities from dynamic data.
problem Reconstructing networks and identifying communities from dynamic data.
method Nonparametric Bayesian approach that simultaneously infers network structure and community membership.
result Joint reconstruction and community detection improve each other's accuracy.
LargeMvC-Net improves scalability of multi-view clustering.
problem Scalability issues in multi-view clustering.
method Deep unfolding of multi-view clustering into a network architecture with three modules.
result LargeMvC-Net consistently outperforms state-of-the-art methods in scalability and effectiveness.
A scalable GPLVM model using stochastic variational inference.
problem Scalable inference for Gaussian process latent variable models.
method Doubly stochastic formulation of Bayesian GPLVM with minibatch training.
result High-fidelity reconstructions in the presence of missing data.
New algorithm reconstructs sparse networks in subquadratic time.
problem Reconstructing sparse networks from limited data.
method Stochastic second neighbor search to bypass quadratic complexity.
result Subquadratic time complexity, up to O(N3/2logN). EggNet reconstructs particle tracks from hits using evolving graph attention networks.
problem Particle track reconstruction is computationally expensive and combinatorial.
method EggNet uses a one-shot object condensation approach with evolving graph attention networks.
result EggNet outperforms methods requiring fixed input graphs on TrackML dataset.
Scalable model checking for stochastic systems using Gaussian Processes and Bayesian Neural Networks.
problem Efficiently verifying properties of stochastic systems with high-dimensional parameter spaces.
method Stochastic Variational Smoothed Model Checking (SV-smMC) using Gaussian Processes and Bayesian Neural Networks.
result SV-smMC scales to larger datasets and enables application to high-dimensional parameter spaces.
Derives kernel PCA with Nyström method for scalability.
problem Scalability of kernel PCA.
method Nyström method for kernel PCA.
result Provides scalable alternative to full kernel PCA.
LAGE is a systematic framework developed in Java. The motivation of LAGE is to provide a scalable and parallel solution to reconstruct Gene Regulatory Networks (GRNs) from continuous gene expression data for very large amount of genes. The basic idea of our framework is motivated by the philosophy of divideand-conquer.…
Method reconstructs neuron models from spike times efficiently.
problem Reconstructing neuron models from spike times in degenerate populations.
method Combining deep learning with DICs to map spike times to DIC densities and generate degenerate CBM populations.
result Fast and scalable reconstruction of degenerate populations from spike recordings.
EnVAE uses energy score for likelihood-free VAEs, improving image reconstructions.
problem Likelihood misspecification in VAEs leads to blurry reconstructions and poor data fidelity.
method Deterministic decoder, energy score as reconstruction loss, fast variant for efficiency.
result EnVAE achieves superior reconstruction and generation quality compared to likelihood-based baselines.
IGNNK uses GNN for spatiotemporal kriging, improving scalability and transferability.
problem Efficiently recovering signals for unsampled locations in spatiotemporal data.
method Developed an Inductive Graph Neural Network Kriging (IGNNK) model to learn spatial message passing.
result IGNNK effectively learns spatial message passing and can be transferred to new graph structures.
Nyström approximation for scalable operator learning
problem Scalability of operator learning for large datasets
method Nyström subsampling with operator learning
result Minimax-optimal convergence rates for functional outputs
SDSR reconstructs species trees from genetic markers efficiently.
problem Challenges in reconstructing species trees from genetic data.
method Spectral divide-and-conquer approach based on graph theory.
result SDSR achieves up to 10-fold faster runtime with comparable accuracy.
Simplifies VAE for anomaly detection using rate-distortion theory.
problem Anomaly detection in unsupervised learning systems.
method Revisit VAE from information theory, incorporate model uncertainty.
result Competitive performance on benchmark datasets.
FsNet selects features for high-dimensional biological data efficiently.
problem Efficient feature selection for high-dimensional biological data.
method FsNet combines selection and reconstruction layers with tiny networks for weight prediction.
result FsNet outperforms standard DNNs on high-dimensional biological datasets.
Simulates multi-asset spot and option markets using normalizing flows.
problem High-dimensionality of market call prices and dynamic preservation across simulators.
method Normalizing flows for efficient low-dimensional representations, conditional invertibility for joint distribution calibration.
result Calibrated simulators maintain dynamics of each underlying and accurately represent market call prices.
New method speeds up kernel-based machine learning for force field reconstruction.
problem Scalability issues in kernel-based machine learning for force field reconstruction.
method Nyström-type methods to construct preconditioners based on low-rank approximations of the kernel matrix.
result Effective preconditioners lead to super-linear convergence in kernel-based machine learning.
Efficient method for learning continuous exponential families beyond Gaussian.
problem Learning continuous exponential families with unbounded support.
method Interaction Screening approach for scalable learning of continuous graphical models.
result Our estimator maintains similar accuracy and sample complexity scalings compared to alternative approaches, while improving run-time.
Generalizes adversarial learning for better latent variable inference in GANs.
problem Improving latent variable inference in GANs for diverse applications.
method Adversarial learning with multiple feedback layers, self-supervision, and auxiliary tasks.
result Achieves global optimum matching multiple joint distributions.
Paper tackles active learning with Gaussian processes for complex data.
problem Challenges in real-world data due to noise and structural complexity.
method Develops a model-agnostic active learning framework using Gaussian process regression.
result Demonstrates state-of-the-art performance in reconstructing quantum chemical force fields.
Scalable approach for object pose estimation across domains.
problem Object pose estimation across different datasets and models.
method Multi-path learning: shared encoder, object-specific decoders.
result Generalizes well from synthetic to real data and across various instances.
Many problems of low-level computer vision and image processing, such as denoising, deconvolution, tomographic reconstruction or super-resolution, can be addressed by maximizing the posterior distribution of a sparse linear model (SLM). We show how higher-order Bayesian decision-making problems, such as optimizing imag…
Scalable GPLVM reduces complexity in scRNA-seq data, accounting for technical and biological confounders.
problem Complexity and confounders in scRNA-seq data hamper interpretation.
method Extended Gaussian process latent variable model (GPLVM) to handle large datasets.
result Framework reconstructs latent signatures and captures disease-specific gene expression.
MarkerMap selects key genes for cell type analysis in single-cell RNA-seq.
problem Selecting informative genes from large single-cell RNA-seq datasets is challenging and computationally intensive.
method MarkerMap is a generative model that identifies minimal gene sets explaining cell type variability.
result MarkerMap outperforms existing methods in both supervised and unsupervised marker selection.
A method to control neural level sets for improved generalization and robustness.
problem Improving the properties of neural networks, particularly their decision boundaries and robustness.
method Sampling neural level sets and relating them to network parameters through a sample network.
result High fidelity surface reconstruction from raw 3D point clouds and comparable robust accuracy to state-of-the-art methods.
EPINE enhances network embedding by improving adjacency matrix-based high-order proximity.
problem Inaccurate and poorly designed calculation of high-order proximity in network embedding.
method EPINE redefines high-order proximity intuitively and proposes a scalable algorithm for accurate calculation.
result EPINE outperforms existing methods in network reconstruction, link prediction, and node classification.
COSMO learns DAG structure without acyclicity constraints.
problem Learning DAG structure from data efficiently and without constraints.
method Differentiable approximation of smooth orientation matrix.
result COSMO converges to acyclic solutions without evaluating acyclicity.
Paper uses VAEs and GANs to estimate cryo-EM image orientation and camera parameters.
problem Estimating orientation and camera parameters from noisy cryo-EM images.
method Combines VAEs and GANs to learn latent representation, then designs estimation method.
result Geometric approach for fast cryo-EM biomolecule reconstruction.
TadGAN detects anomalies in time series data using GANs and LSTM.
problem Challenges in detecting anomalies in time series data, especially without labeled data.
method TadGAN uses Generative Adversarial Networks (GANs) with LSTM Recurrent Neural Networks to capture temporal correlations and compute anomaly scores.
result TadGAN outperforms 8 baseline methods in most cases, achieving the highest averaged F1 score.
Contrastive Code Representation Learning improves code summarization and type inference.
problem Code representations are sensitive to edits, hindering downstream semantic understanding tasks.
method ContraCode: a contrastive pre-training task that learns code functionality.
result Contrastive pre-training improves code summarization and type inference accuracy.
StatFEM uses low-rank approximations to scale Bayesian statFEM for high-dimensional problems.
problem Model misspecification and scalability in high-dimensional physical systems.
method Low-rank approximation of covariance matrix, Bayesian filtering, sparse data reconstruction.
result Reconstructs sparsely observed data-generating processes with minimal loss of information.
Extends GP models for sequential data, scalable and robust.
problem Handling sequential input-output observations in multi-task settings.
method Variational inference with sparse approximations and recursive GP priors.
result Tractable continual learning with KL divergences and recursive reconstruction.
DEFRAG accelerates extreme classification by reducing feature dimensions.
problem High precision and scalability in assigning labels from a vast label space.
method Adaptive feature agglomeration to reduce feature dimensions.
result Significant reduction in training and prediction times (up to 40%) for extreme classification algorithms.
daep learns from irregular, multimodal astronomical data.
problem Learning from irregular, multimodal astronomical sequences.
method Diffusion Autoencoder with Perceivers (daep) tokenizes, compresses, and reconstructs data.
result daep outperforms VAE and maep baselines in reconstruction and fine-scale structure preservation.
GeoFunFlow tackles inverse problems on complex geometries with efficient learning.
problem Challenges in inverse problems governed by PDEs, especially on irregular geometries.
method Combines geometric function autoencoder and latent diffusion model trained via rectified flow.
result Achieves state-of-the-art reconstruction accuracy and efficient inference.
A scalable method for Bayesian inference in large linear models.
problem High computational cost in Bayesian linear models for large networks.
method Sample-based inference and g-prior for hyperparameter selection.
result Linearised neural network inference on large datasets (ResNet-18, ResNet-50, U-Net).
A new neural subsampling method reduces data volume for deep models.
problem Efficiently process huge volumes of high-dimensional data like images.
method Two-stage end-to-end neural subsampling model that optimizes for arbitrary downstream tasks.
result Outperforms baselines under low subsampling rates on various tasks.
Develops scalable Bayesian inference methods for neural networks.
problem Lack of model uncertainty in deep learning leading to overconfident predictions.
method Linearised Laplace approximation, conjugate Gaussian-linear models, stochastic gradient descent, sample-based EM algorithm.
result Equips neural networks with model uncertainty using scalable methods.
Reconstructing the causal network in a complex dynamical system plays a crucial role in many applications, from sub-cellular biology to economic systems. Here we focus on inferring gene regulation networks (GRNs) from perturbation or gene deletion experiments. Despite their scientific merit, such perturbation experimen…
This paper proposes a probabilistic imputation method with uncertainty quantification.
problem Missing value imputation with uncertainty estimation for large datasets.
method Low Rank Gaussian Copula framework that augments PPCA with column-specific transformations.
result The method yields state-of-the-art imputation accuracy and well-calibrated uncertainty estimates.
New algorithm predicts missing matrix entries using side information, outperforming existing methods.
problem Learning a partially observed matrix with side information.
method Mixed-projection ADMM algorithm for optimization.
result Our algorithm achieves 2.3% lower objective value and 41% lower reconstruction error than benchmarks.
LightSecAgg reduces secure aggregation complexity in FL.
problem Complexity in secure aggregation protocols for FL systems.
method One-shot aggregate-mask reconstruction via mask encoding/decoding.
result Significantly reduces overhead for resiliency against dropped users.
An axiomatic approach to signal reconstruction is formulated, involving a sample consistent set and a guiding set, describing desired reconstructions. New frame-less reconstruction methods are proposed, based on a novel concept of a reconstruction set, defined as a shortest pathway between the sample consistent set and…